{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:59:30Z","timestamp":1767322770309,"version":"3.48.0"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032113160","type":"print"},{"value":"9783032113177","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-11317-7_38","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:55:19Z","timestamp":1767322519000},"page":"457-469","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Real-Time System for\u00a0Egocentric Hand-Object Interaction Detection in\u00a0Industrial Domains"],"prefix":"10.1007","author":[{"given":"Antonio","family":"Finocchiaro","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alessandro Sebastiano","family":"Catinello","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3466-5555","authenticated-orcid":false,"given":"Michele","family":"Mazzamuto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8693-3826","authenticated-orcid":false,"given":"Rosario","family":"Leonardi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6911-0302","authenticated-orcid":false,"given":"Antonino","family":"Furnari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6034-0432","authenticated-orcid":false,"given":"Giovanni Maria","family":"Farinella","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"38_CR1","doi-asserted-by":"crossref","unstructured":"An, J., Kang, H., Han, S.H., Yang, M.H., Kim, S.J.: Miniroad: minimal RNN framework for online action detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10341\u201310350 (2023)","DOI":"10.1109\/ICCV51070.2023.00949"},{"key":"38_CR2","doi-asserted-by":"crossref","unstructured":"Chen, G., et al.: Video mamba suite: state space model as a versatile alternative for video understanding. arXiv preprint arXiv:2403.09626 (2024)","DOI":"10.1007\/s11263-025-02597-y"},{"key":"38_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, T., Song, L., Ge, Y., Liu, W., Wang, X., Shan, Y.: Yolo-world: real-time open-vocabulary object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.01599"},{"key":"38_CR4","first-page":"13745","volume":"35","author":"A Darkhalil","year":"2022","unstructured":"Darkhalil, A., et al.: Epic-kitchens visor benchmark: video segmentations and object relations. Adv. Neural. Inf. Process. Syst. 35, 13745\u201313758 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"38_CR5","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"38_CR6","unstructured":"Leonardi, R., Ragusa, F., Furnari, A., Farinella, G.M.: Exploiting multimodal synthetic data for egocentric human-object interaction detection in an industrial scenario. Comput. Vision Image Understanding"},{"key":"38_CR7","doi-asserted-by":"crossref","unstructured":"Mazzamuto, M., Ragusa, F., Resta, A., Farinella, G. M., Furnari, A.: A wearable device application for human-object interactions detection. In: VISIGRAPP (4: VISAPP), pp. 664\u2013671 (2023)","DOI":"10.5220\/0011725800003417"},{"key":"38_CR8","unstructured":"Oquab, M., et\u00a0al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"38_CR9","doi-asserted-by":"crossref","unstructured":"Ragusa, F., et al.: Enigma-51: towards a fine-grained understanding of human-object interactions in industrial scenarios. arXiv preprint arXiv:2309.14809 (2023)","DOI":"10.1109\/WACV57701.2024.00449"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Ragusa, F., Furnari, A., Livatino, S., Farinella, G.M.: The meccano dataset: understanding human-object interactions from egocentric videos in an industrial-like domain. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1569\u20131578 (2021)","DOI":"10.1109\/WACV48630.2021.00161"},{"key":"38_CR11","doi-asserted-by":"crossref","unstructured":"Shan, D., Geng, J., Shu, M., Fouhey, D.F.: Understanding human hands in contact at internet scale (2020)","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"38_CR12","doi-asserted-by":"crossref","unstructured":"Shou, Z., et al.: Online detection of action start in untrimmed, streaming videos. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 534\u2013551 (2018)","DOI":"10.1007\/978-3-030-01219-9_33"},{"key":"38_CR13","unstructured":"Tan, M., Le, Q.: Efficientnetv2: smaller models and faster training. In: International Conference on Machine Learning, pp. 10096\u201310106. PMLR (2021)"},{"key":"38_CR14","doi-asserted-by":"crossref","unstructured":"Wang, x., et al.: Oadtr: online action detection with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7565\u20137575 (2021)","DOI":"10.1109\/ICCV48922.2021.00747"},{"key":"38_CR15","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhou, S., Stent, S., Shi, J.: Fine-grained egocentric hand-object segmentation: Dataset, model, and applications. In: European Conference on Computer Vision, pp. 127\u2013145. Springer (2022)","DOI":"10.1007\/978-3-031-19818-2_8"},{"key":"38_CR16","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Kr\u00e4henb\u00fchl, P.: Real-time online video detection with temporal smoothing transformers. In: European Conference on Computer Vision, pp. 485\u2013502. Springer (2022)","DOI":"10.1007\/978-3-031-19830-4_28"},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"Zou, C., et\u00a0al.: End-to-end human object interaction detection with hoi transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11825\u201311834 (2021)","DOI":"10.1109\/CVPR46437.2021.01165"}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing - ICIAP 2025 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-11317-7_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:55:21Z","timestamp":1767322521000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-11317-7_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032113160","9783032113177"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-11317-7_38","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Rome","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iciap.org\/home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}